paper-with-me

홈 › Papers

EUDA: An Efficient Unsupervised Domain Adaptation via Self-Supervised Vision Transformer

2024-07-31 · Ali Abedi, Q. M. Jonathan Wu, Ning Zhang, Farhad Pourpanah

Unsupervised domain adaptation (UDA) aims to mitigate the domain shift issue, where the distribution of training (source) data differs from that of testing (target) data. Many models have been developed to tackle this problem, and recently vision transformers (ViTs) have shown promising results. However, the complexity and large number of trainable parameters of ViTs restrict their deployment in practical applications. This underscores the need for an efficient model that not only reduces trainable parameters but also allows for adjustable complexity based on specific needs while delivering comparable performance. To achieve this, in this paper we introduce an Efficient Unsupervised Domain Adaptation (EUDA) framework. EUDA employs the DINOv2, which is a self-supervised ViT, as a feature extractor followed by a simplified bottleneck of fully connected layers to refine features for enhanced domain adaptation. Additionally, EUDA employs the synergistic domain alignment loss (SDAL), which integrates cross-entropy (CE) and maximum mean discrepancy (MMD) losses, to balance adaptation by minimizing classification errors in the source domain while aligning the source and target domain distributions. The experimental results indicate the effectiveness of EUDA in producing comparable results as compared with other state-of-the-art methods in domain adaptation with significantly fewer trainable parameters, between 42% to 99.7% fewer. This showcases the ability to train the model in a resource-limited environment. The code of the model is available at: https://github.com/A-Abedi/EUDA.

📄 PDF Abstract BibTeX arXiv:2407.21311

Code (1)

a-abedi/euda 공식 구현 pytorch

Tasks

Domain AdaptationUnsupervised Domain Adaptation

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
Attention 설명 없음
Multi-Head Attention 설명 없음
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Similar Papers 제목 키워드 기반

Heterogeneous domain adaptation: An unsupervised approach

2017-01-10 · Feng Liu, Guanquan Zhang, Jie Lu

Domain adaptation leverages the knowledge in one domain - the source domain - to improve learning efficiency in another domain - the target domain. Existing heterogeneous domain adaptation research is relatively well-pro…

Domain Adaptationtext-classificationText ClassificationTransfer Learning+1

MSDA: Combining Pseudo-labeling and Self-Supervision for Unsupervised Domain Adaptation in ASR

2025-05-30 · Dimitrios Damianos, Georgios Paraskevopoulos, Alexandros Potamianos

In this work, we investigate the Meta PL unsupervised domain adaptation framework for Automatic Speech Recognition (ASR). We introduce a Multi-Stage Domain Adaptation pipeline (MSDA), a sample-efficient, two-stage adapta…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Domain AdaptationSelf-Supervised Learning+3

Geometric Unsupervised Domain Adaptation for Semantic Segmentation

2021-03-30 · ICCV 2021 10 · Vitor Guizilini, Jie Li, Rares Ambrus, Adrien Gaidon

Simulators can efficiently generate large amounts of labeled synthetic data with perfect supervision for hard-to-label tasks like semantic segmentation. However, they introduce a domain gap that severely hurts real-world…

Depth EstimationDepth PredictionDomain AdaptationMonocular Depth Estimation+3

Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation

2021-03-31 · CVPR 2021 1 · Xiangyu Yue, Zangwei Zheng, Shanghang Zhang, Yang Gao 외

Unsupervised Domain Adaptation (UDA) transfers predictive models from a fully-labeled source domain to an unlabeled target domain. In some applications, however, it is expensive even to collect labels in the source domai…

Contrastive LearningDomain AdaptationSelf-Supervised LearningSemantic Segmentation+1

Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation

2019-09-02 · ICCV 2019 10 · Jaehoon Choi, Taekyung Kim, Changick Kim

Deep learning-based semantic segmentation methods have an intrinsic limitation that training a model requires a large amount of data with pixel-level annotations. To address this challenging issue, many researchers give …

Data AugmentationDomain AdaptationSegmentationSemantic Segmentation+1